CN112529585A

CN112529585A - Interactive awakening method, device, equipment and system for risk transaction

Info

Publication number: CN112529585A
Application number: CN202011426843.XA
Authority: CN
Inventors: 刘赛帅; 王子豪
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2020-12-09
Filing date: 2020-12-09
Publication date: 2021-03-19

Abstract

The present specification provides an interactive awakening method, an interactive awakening device, an interactive awakening apparatus and an interactive awakening system for risk transaction, which actively interact with a transaction user to be processed for risk transaction, perform intention identification and session recommendation, splice determined interactive answering information and recommended risk interaction inquiry information, and send the spliced information to the transaction user, so as to guide the transaction user to perform multiple rounds of interactive awakening sessions. Based on multiple rounds of conversations with transaction users, risk identification and confirmation of risk transactions are achieved, the risk identification accuracy of the risk transactions is improved, fraud means of the risk transactions can be mined, and a data base is laid for identification of subsequent risk transactions. Meanwhile, by splicing the interactive question answering information and the recommended risk interactive inquiry information, the question of the trading user is answered, the trading user can be actively guided to confirm the risk trading, the trading user is awakened in time, and the safety of network trading and the awakening rate of the risk trading are improved.

Description

Interactive awakening method, device, equipment and system for risk transaction

Technical Field

The present specification belongs to the field of computer technologies, and in particular, to an interactive wake-up method, apparatus, device, and system for risk transaction.

Background

The network transaction facilitates the life of people, meanwhile, some risk transactions are also induced, and some lawbreakers use the internet to implement fraud transactions, so that loss is brought to users. To protect the user from being cheated to block the risky transactions, but the user is deeply cheated in the cheating, if the corresponding cheating techniques cannot be well explained to the user, the user may try to pay and continue to be cheated by bypassing the governing imagination. At present, the specific fraud method of the risk transaction is difficult to judge only through static data, meanwhile, the high-risk transaction behavior is judged partially through the static data and may be the normal transaction of the user, and when the specific fraud method whether the user is really cheated or cheated is not determined, the transaction is directly blocked, so that bad experience is brought to the user.

Disclosure of Invention

An object of the embodiments of the present specification is to provide a method, an apparatus, a device, and a system for interactive wake-up of risk transactions, which improve accuracy of risk identification of risk transactions and wake-up rate of risk transactions.

In one aspect, an embodiment of the present specification provides an interactive wake-up method for risk transaction, where the method includes:

sending risk reminding interactive information to a transaction user of the risk transaction to be processed, and receiving risk confirmation interactive information returned by the transaction user;

determining the interaction intention of the trading user according to the risk confirmation interaction information, and acquiring interaction answering information corresponding to the interaction intention from a question and answer database;

confirming interaction information according to the interaction intention and the risk, and determining risk interaction inquiry information;

splicing the interactive question answering information and the risk interactive inquiry information to obtain risk interactive splicing information;

and sending the risk interaction splicing information to the trading user so as to guide the trading user to carry out interactive awakening of multiple rounds of risk trading.

In another aspect, the present specification provides an interactive wake-up device for risk transactions, comprising:

the risk reminding module is used for sending risk reminding interactive information to a transaction user of the risk transaction to be processed and receiving risk confirmation interactive information returned by the transaction user;

the intention identification module is used for determining the interaction intention of the trading user according to the risk confirmation interaction information and acquiring interaction answering information corresponding to the interaction intention from a question and answer database;

the dialogue recommendation module is used for confirming the interaction information according to the interaction intention and the risk and determining risk interaction inquiry information;

the session splicing module is used for splicing the interactive answering information and the risk interactive inquiry information to obtain risk interactive splicing information;

and the multi-round interaction module is used for sending the risk interaction splicing information to the trading user so as to guide the trading user to carry out interactive awakening of multi-round risk transactions.

In another aspect, an embodiment of the present specification provides an interactive wake-up device for risk transaction, including at least one processor and a memory for storing processor-executable instructions, where the processor executes the instructions to implement the interactive wake-up method for risk transaction.

In yet another aspect, an embodiment of the present specification provides an interactive wake-up system for risk transaction, including: the intelligent conversation robot and the user terminal;

the intelligent dialogue robot comprises at least one processor and a memory for storing processor executable instructions, and when the processor executes the instructions, the interactive awakening method of the risk transaction is realized;

the user terminal comprises at least one processor and a memory for storing processor-executable instructions, and the processor executes the instructions to realize multiple rounds of interaction with the intelligent dialogue robot.

According to the interactive awakening method, the interactive awakening device, the interactive awakening equipment and the interactive awakening system for the risk transaction, interaction is actively carried out with a transaction user of the risk transaction to be processed, intention identification and dialogue recommendation are carried out based on information returned by the transaction user, and corresponding interactive answering information is obtained based on the interactive intention of the transaction user. And splicing the determined interactive answering information and the recommended risk interactive inquiry information, and then sending the spliced interactive answering information and the recommended risk interactive inquiry information to the trading user to guide the trading user to carry out multiple rounds of interactive awakening conversations. Based on multiple rounds of conversations with transaction users, risk identification and confirmation of risk transactions are achieved, the risk identification accuracy of the risk transactions is improved, fraud means of the risk transactions can be mined, and a data base is laid for identification of subsequent risk transactions. Meanwhile, by splicing the interactive question answering information and the recommended risk interactive inquiry information, the question of the trading user is answered, the trading user can be actively guided to confirm the risk trading, the trading user can intuitively feel whether the risk trading really has the risk or not, the trading user is timely awakened, and the safety of network trading and the awakening rate of the risk trading are improved.

Drawings

In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.

Fig. 1 is a schematic flowchart of an embodiment of an interactive wake-up method for risk transaction provided in an embodiment of the present specification;

FIG. 2 is a schematic flow diagram of an intent to abstract in some embodiments of the present description;

FIG. 3 is a schematic block diagram of an interactive wake-up of risk transactions in one embodiment of the present description;

FIG. 4 is a block diagram of an embodiment of an interactive wake-up apparatus for risk transaction provided in the present specification;

fig. 5 is a block diagram of a hardware structure of an interactive wake-up server for risk transaction in one embodiment of the present specification.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present specification, and not all of the embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the present specification without any inventive step should fall within the scope of protection of the present specification.

With the popularization of online transactions, online fraud is increasing, and risk management and control are required to be performed on transactions with possible risks. Generally, for a possible risk transaction, a person may need to communicate with a transaction user to determine whether the transaction really has a risk, and wake up the transaction user in time, but the labor cost is high, the risk transaction cannot be confirmed in a matching manner, and the service quality of all service staff cannot be guaranteed.

Fig. 1 is a flowchart schematically illustrating an embodiment of an interactive wake-up method for risk transaction provided in an embodiment of the present specification. Although the present specification provides the method steps or apparatus structures as shown in the following examples or figures, more or less steps or modules may be included in the method or apparatus structures based on conventional or non-inventive efforts. In the case of steps or structures which do not logically have the necessary cause and effect relationship, the execution order of the steps or the block structure of the apparatus is not limited to the execution order or the block structure shown in the embodiments or the drawings of the present specification. When the described method or module structure is applied to a device, a server or an end product in practice, the method or module structure according to the embodiment or the figures may be executed sequentially or in parallel (for example, in a parallel processor or multi-thread processing environment, or even in an implementation environment including distributed processing and server clustering).

In a specific embodiment, as shown in fig. 1, in an embodiment of the interactive wake-up method for risk transaction provided in this specification, the method may be applied to a transaction platform, specifically, a computer, a tablet computer, a smart phone, and other terminals, and the method may include the following steps:

102, sending risk reminding interactive information to a transaction user of the risk transaction to be processed, and receiving risk confirmation interactive information returned by the transaction user.

In a specific implementation process, when the risk management and control system of the transaction platform identifies that a risk may exist in a current transaction, the transaction can be used as a pending risk transaction and transferred to an interactive awakening system of the risk transaction. At this time, the transaction user in the pending risk transaction may be actively contacted, and risk reminding interactive information may be sent to the transaction user, where the transaction user may generally be understood as a payer in the pending risk transaction, and the risk reminding interactive information may include: the self-introduction, the purpose of communicating with the user, and the identity confirmation of the transaction user may also include other contents, and the specific content of the interactive information is not specifically limited in this specification. After receiving the risk reminding interactive information sent by the system, the trading user can reply according to the received content, and at the moment, the system can receive the risk confirmation interactive information returned by the trading user. The risk confirmation interaction information may include information such as identity confirmation, interaction inquiry, and the like, and the embodiments of the present specification are not particularly limited.

For example: in one scenario example, after determining that a transaction is at risk, send "do you, i.e., XX fraud center customer service, i wake up, ask you for mr. X? "as risk alert interaction information. The trading user may then reply back to "what, i, what? "confirm mutual information as risk.

And step 104, determining the interaction intention of the trading user according to the risk confirmation interaction information, and acquiring the interaction answering information corresponding to the interaction intention from a question-answer database.

In a specific implementation process, after the risk confirmation interaction information returned by the trading user is received, the intention identification can be carried out on the received risk confirmation interaction information to determine the interaction intention of the trading user. After the interaction intention is determined, the interaction answering information corresponding to the interaction intention can be obtained from a question-answer database, wherein the question-answer database can include common user interaction intentions and corresponding answering information.

In some embodiments of this specification, an FAQ (frequencytly activated questions) intention recognition model may be pre-constructed, model training is performed in advance based on a historical interaction log, an FAQ intention recognition model is constructed, and the constructed FAQ recognition model is used to perform intention recognition on risk confirmation interaction information returned by a trading user, so as to recognize an interaction intention of the trading user. And matching corresponding interactive question answering information based on the interactive intention. The FAQ intention recognition model can be a multi-classification model of Bert (bidirectional Encoder reproduction from transformations), only needs a small amount of manual labeling samples for training, supports recognition of multiple intentions in user dialog, takes the user dialog as input, and can predict the interaction intention hit by the dialog. Of course, other intelligent learning models may be selected according to actual needs to perform intent recognition on the risk confirmation interaction information returned by the transaction user or perform intent recognition by using expert strategies and the like, and embodiments of the present specification are not particularly limited.

And 106, determining risk interaction inquiry information according to the interaction intention and the risk confirmation interaction information.

In a specific implementation process, after the interaction intention of the trading user is determined, the interaction information can be confirmed according to the interaction intention of the trading user and the risk returned by the trading user, and the current risk interaction inquiry information, namely the current interaction dialogue information is recommended. The risk interaction query information may be understood as a question in the current dialog that the user is required to answer, or a question that has to be queried in order to risk confirm the risk of the risk transaction. In some embodiments of the present description, model training may be performed based on a historical interaction log to construct a conversation recommendation model, and the conversation recommendation model may be used to recommend risk interaction query information that needs to be interacted with a user currently based on current interaction content and an interaction purpose. For example: the main purpose of interaction in the implementation of this specification may be to perform risk identification confirmation and mining a back real fraud technique through a dialog, and the dialog recommendation model may recommend key problems of risk identification interaction based on the content of the current interaction, such as: critical questions of the transaction user's relationship with the payee, whether to transact himself, etc. serve as risk interaction query information.

The intention recognition and the dialogue recommendation in the embodiment of the description are performed separately, that is, the FAQ intention recognition model and the dialogue recommendation model are divided into two modules for training, so that the stability of the dialogue recommendation model and the flexibility of the FAQ intention recognition are guaranteed, and in the form of splicing the robot dialogue, the answering scene is more diversified, and the question recommended by the dialogue module is continuously asked after the answer.

In some embodiments of the present specification, said determining risk interaction inquiry information according to the interaction intention and the risk confirmation interaction information includes:

if the interaction intention is to change to manual service, the risk interaction inquiry information is to change to manual reservation;

and if the interaction intention is to refuse communication or the risk confirmation interaction information is that the identity information is not consistent, the risk interaction inquiry information is communication ending information.

In a specific implementation process, when the interaction intention of the transaction user is identified as manual service, the risk interaction inquiry information at the moment can be a manual reservation. When the interaction intention of the transaction user is recognized as refusal communication: when the risk confirmation interaction information returned by the trading user is the information which is not used, unnecessary and the like and refuses communication, or the risk confirmation interaction information returned by the trading user is the identity information, the identity information is not consistent: when inquiring whether the transaction user is mr. X, the transaction user replies no, and at this time, the risk interaction inquiry information may be communication ending information, such as: "then do not disturb you first, thank you for listening, see again". When the transaction user is identified to wish to transfer to manual service, the transaction user can skip to the manual service process in time, so that the user experience is improved, and the interruption of identification and confirmation of the risk transaction caused by the user hanging up due to the reaction is avoided. Meanwhile, when the fact that the user does not want to communicate or the user information is wrong is recognized, the conversation is ended in time, the requirement of the user is responded in time, unnecessary troubles are avoided for the user, and the user experience is improved.

And step 108, splicing the interactive answering information and the risk interactive inquiry information to obtain risk interactive splicing information.

In a specific implementation process, after the interactive answer information and the risk interactive inquiry information of the current interaction are obtained, the interactive answer information and the risk interactive inquiry information can be spliced to obtain risk sister splicing information. Generally, when splicing is performed, risk interaction inquiry information can be added to the interaction question answering information, so that a transaction user can see the answer to the question at first glance, and the user is guided to perform subsequent interaction.

And step 110, sending the risk interaction splicing information to the trading user so as to guide the trading user to carry out interactive awakening of multiple rounds of risk trading.

In a specific implementation process, the risk interaction splicing information obtained by splicing is sent to the trading user, the trading user can perform the next round of interaction according to the risk interaction inquiry information in the received risk interaction splicing information, multi-round interaction of risk trading is achieved, the trading user can intuitively feel whether the risk transaction to be processed really has a risk or not, the trading user is awakened in time, and the trading safety is improved.

In some embodiments of this specification, the sending the risk interaction splicing information to the trading user to guide the trading user to perform interactive awakening of multiple rounds of risk transactions includes:

sending the risk interaction splicing information to the trading user, and receiving risk dialogue information returned by the trading user;

determining the interaction intention, the interaction answering information and the risk interaction inquiry information of the transaction user in the next round of interaction based on the risk dialogue information;

splicing the interactive question answering information in the next round of interaction with the risk interactive inquiry information in the next round of interaction to obtain risk interactive splicing information in the next round of interaction;

and sending the risk interaction splicing information in the next round of interaction to the trading user, and guiding the trading user to carry out the next round of interaction until the interaction is finished.

In a specific implementation process, after the risk interaction splicing information is obtained, the risk interaction splicing information can be sent to the trading user, the trading user is guided to return to risk interaction inquiry information in the risk interaction splicing information, risk dialogue information returned by the trading user is obtained, and the next round of risk transaction awakening interaction is carried out. And based on the risk dialogue information returned by the trading user, performing intention identification, identifying the interaction intention of the trading user in the next round of interaction, and acquiring interactive question answering information corresponding to the interaction intention from a question answering database. Meanwhile, based on the identified interaction intention of the trading user in the next round of interaction and risk dialogue information returned by the trading user, risk interaction inquiry information in the next round of interaction is determined. And splicing the obtained interactive question answering information in the next round of interaction and the risk interactive inquiry information in the next round of interaction to obtain risk interactive splicing information in the next round of interaction, sending the obtained new risk interactive splicing information to the trading user, and guiding the trading user to carry out the next round of interaction. And repeating the steps of the embodiment, and performing a new round of intention identification, dialogue recommendation and dialogue splicing until the interaction is finished, thereby realizing multi-round interactive awakening of risk transaction.

The interactive awakening method for risk transaction provided by the embodiment of the specification actively interacts with the transaction user to be processed with risk transaction, performs intention identification and dialogue recommendation based on information returned by the transaction user, and acquires corresponding interactive answering information based on the interactive intention of the transaction user. And splicing the determined interactive answering information and the recommended risk interactive inquiry information, and then sending the spliced interactive answering information and the recommended risk interactive inquiry information to the trading user to guide the trading user to carry out multiple rounds of interactive awakening conversations. Based on multiple rounds of conversations with transaction users, risk identification and confirmation of risk transactions are achieved, the risk identification accuracy of the risk transactions is improved, fraud means of the risk transactions can be mined, and a data base is laid for identification of subsequent risk transactions. Meanwhile, by splicing the interactive question answering information and the recommended risk interactive inquiry information, the question of the trading user is answered, the trading user can be actively guided to confirm the risk trading, the trading user can intuitively feel whether the risk trading really has the risk or not, the trading user is timely awakened, and the safety of network trading and the awakening rate of the risk trading are improved.

On the basis of the above embodiments, in some embodiments of the present specification, the method for constructing the question-answer database includes:

acquiring historical risk transaction interaction sample information;

marking a question interaction log with questions from the historical risk transaction interaction sample information;

and clustering the query interaction logs through a clustering algorithm to obtain a main stream interaction intention, and storing the main stream interaction intention and the interactive answer information corresponding to the main stream interaction intention into the question-answer database.

In a specific implementation process, fig. 2 is a schematic flow diagram intended to be refined in some embodiments of the present specification, and as shown in fig. 2, the embodiment of the present specification may obtain a plurality of pieces of historical risk transaction interaction sample information, that is, a dialog log in fig. 2, may mark a question interaction log having a question from the obtained historical risk transaction interaction sample information, and the obtaining of the question interaction log may be performed by manually marking or scanning a keyword using an intelligent learning algorithm, and the embodiment of the present specification is not particularly limited. After the query interaction logs are obtained, cluster analysis can be performed on the query interaction logs by using a clustering algorithm to obtain a mainstream interaction intention, as shown in fig. 2, in some embodiments of the present description, after the query interaction logs are subjected to cluster analysis, a plurality of query classes can be obtained first, and then manual review is used to screen out a main intention which is high in use frequency or needs to be answered as the mainstream interaction intention. After the main stream interaction intention is obtained, the interaction answering information of the main stream interaction intention can be obtained from the historical risk transaction interaction sample information, the interaction answering information of the main stream interaction intention can be obtained by refining, synthesizing and the like of the answering information in the historical risk transaction interaction sample information, and the main stream interaction intention and the interaction answering information corresponding to the main stream interaction intention are stored in a question-answer database. The method has the advantages that the question-answer database is constructed by utilizing historical risk transaction interactive contents, a data base is laid for intention identification of subsequent risk transactions, the question logs of the users are clustered, a few question-answer scenes are focused, the need of manual examination is reduced, and the purpose of solving the questions of the users as many as possible by using few question-answer schemes is achieved.

In some embodiments of the present specification, after marking the query interaction log for which a query exists, the method further comprises:

expanding the query interaction log by using a similarity algorithm to obtain an expanded query interaction log;

the clustering the query interaction logs by a clustering algorithm comprises:

and clustering the expanded query interaction logs through a clustering algorithm to obtain the mainstream interaction intention.

In a specific implementation process, after the query interaction logs with questions are marked, the marked query interaction logs can be expanded by using a similarity algorithm to obtain expanded query interaction logs. And clustering the expanded query interaction logs by using a clustering algorithm to obtain query classes, and manually auditing to obtain a main stream interaction intention. A small number of query interaction logs can be expanded from a large number of user dialog logs through a small number of manual labels and a similar algorithm, a large number of sample data is obtained, the marking cost is reduced, and the data processing efficiency is improved.

In some embodiments of the present specification, the determining the interaction intention of the trading user according to the risk confirmation interaction information, and obtaining the interaction question information corresponding to the interaction intention from a question-answer database includes:

and determining the interaction intentions of the trading user according to the risk confirmation interaction information, and if the number of the interaction intentions is greater than 1, acquiring the interaction answering information corresponding to the interaction intention with the highest priority from a question-answering database according to the preset priority of the interaction intentions.

In a specific implementation process, different priorities of the interaction intentions can be configured in advance, and if intention identification is performed on risk confirmation interaction information returned by a trading user, and the number of the identified interaction intentions is greater than 1, the interaction intentions with high priority can be preferentially answered according to the preconfigured priorities, namely, the interaction answering information corresponding to the interaction intention with the highest priority is obtained from the question answering database. For example: the priority of interaction intention A is configured to be 1 in advance, the priority of interaction intention B is configured to be 2, the priority of interaction intention C is configured to be 3, intention identification is carried out on risk confirmation interaction information returned by a trading user, and if the identified interaction intention has interaction intents A and C, interaction answering information corresponding to the interaction intention A can be obtained from a question and answer database and is used as answering information of the interaction and replied to the user.

Through the mode of pre-configuring the priority, the interaction intentions which are important or urgent and known by the user can be responded preferentially, the situation that the user cannot understand the interaction intentions caused by simultaneously answering a plurality of questions is avoided, the most important questions can be answered in time, and the interaction effect and the user experience are improved.

On the basis of the above embodiments, in some embodiments of the present specification, the determining an interaction intention of the trading user according to the risk confirmation interaction information, and acquiring interaction question information corresponding to the interaction intention from a question-answer database includes:

and determining the interaction intentions of the trading user according to the risk confirmation interaction information, if the number of the interaction intentions is more than 1, integrating the specified interaction intentions in the determined interaction intentions according to a preset intention integration rule to obtain integrated interaction intentions, and acquiring the interaction answering information corresponding to the integrated interaction intentions from a question-answering database.

In a specific implementation process, the questions which are usually inquired together by the user or the questions with relatively large relevance can be obtained according to the historical interaction log, the intention integration rule of the interaction intention is configured, and meanwhile, the integrated interaction answering information corresponding to the interaction intention can be stored in the question and answer database based on the integration of different interaction intentions. And when the intention identification is carried out on the risk confirmation interactive information returned by the transaction user and the number of the identified interactive intentions is more than 1, integrating the specified interactive intentions in the identified interactive intentions according to a preset intention integration rule to obtain integrated interactive intentions, and then obtaining interactive answering information corresponding to the integrated interactive intentions from a question and answer database. For example: if, through analysis of the historical interaction log, it is found that the user may have asked question a and question B together, the intent integration rules may be configured such that the interaction intents A, B may be integrated together to answer. When the intention recognition is performed on the risk confirmation interaction information returned by the transaction user, and the recognized interaction intention is A, B, C, the interaction intentions A, B may be integrated together based on a pre-configured intention integration rule to obtain an interaction intention AB, and then the interaction answering information corresponding to the interaction intention AB is obtained from the question and answer database.

The intention integration rule is configured for common questions, so that multiple questions of the user can be answered at one time, and the interaction efficiency is improved.

Fig. 3 is a schematic diagram of a principle framework of interactive wake-up of risk transaction in an embodiment of the present specification, as shown in fig. 3, in the embodiment of the present specification, an ASR (Automatic Speech Recognition) module and a TTS (Text To Speech ) module are added with an FAQ intent Recognition module and a dialog splicing module, after a user query intent is recognized, a corresponding answer is given according To different intentions, and a question in an original main flow is continuously asked, different dialog splicing schemes need To be formulated for different queries, and when a user hits multiple query intentions, i can respond To one of the multiple query intentions, and a priority needs To be formulated in advance. On the basis of not influencing the original conversation process, an FAQ recognition module is added to recognize user questions and give out answer words. And different dialogue splicing schemes are adopted according to different answering words and answering strategies, so that the method is more flexible, a given dialogue target is completed, the user question is responded, the user is more willing to communicate with the robot, and the dialogue strategy is more flexible in a splicing mode.

Examples of interactive processes with and without an FAQ module are given below to more clearly understand the effects brought by the embodiments of the present specification:

1. example of adding FAQ:

the system comprises the following steps: your good, i am XX anti-fraud center customer service, i wake up asking for mr. X?

The user: how did you be? (hit interaction intention "ask incoming call intention")

The system comprises the following steps: give you a call because the system detects that there may be a fraud risk just in the XX transaction, and does you delay your 1 minute and ask you for verification? (splicing manner one, splicing after a question answering process 'asking for a question' without knowing the matching intention of the user

The user: and, what is the transaction? (hit interaction intention "Inquiry amount")

The system comprises the following steps: see here a transaction of three thousand dollars just lost in XX payments asking what person you are transferring to? (splicing mode two, splicing recommended question after answering when the robot has question)

The user: without checking the bar, you turn me manual and i want to pay. (hit interaction intention "go to Man")

The system comprises the following steps: your appointment i has recorded, please keep the call unblocked, and later there will be manual customer service calling you back. (splicing mode three, when the user has the manual appeal, directly jumping out of the conversation process without any question follow-up)

The user: good, thank you.

The system comprises the following steps: then you will not disturb you first, thank you for listening, see later.

2. Example without adding FAQ:

The user: how did you be?

The system comprises the following steps: that is, we recognize that there is a risk of fraud in the transaction just described by three thousand dollars on XX, and that do you check with you for asking can? (preset talk of robot, not answering question)

The user: and, what is the transaction? (the user may not hear the just broadcast clearly, ask again for the transaction)

The system comprises the following steps: the transaction you just failed to pay is what is the transfer of money? (preset talk of robot, not answering question)

The user: without checking the bar, you turn me manual and i want to pay.

The system comprises the following steps: what is that other party your? (preset talk of robot, not answering question)

The user hangs up.

Through the comparison, after the FAQ is added, the question of the user can be answered while risk information of risk transaction is mined, so that the user and the system are guided to carry out risk identification and mining of the risk transaction together, the experience of the user is improved, the problem that the user is not well on-hook due to experience is avoided, the risk transaction is not awakened successfully, and the awakening rate of the risk transaction and the safety of network transaction are improved.

The embodiment of the specification can identify the condition that the user does not cooperate with answering the robot problem but puts forward the question of the user in the conversation process, and the corresponding answering words are made according to the business requirements, so that the user can be effectively saved, and meanwhile, the problem to be asked is put forward to guide the user to carry out risk mining and identification. Intention recognition and dialogue recommendation are trained and predicted independently, the risk of reduction of dialogue recommendation stability caused by FAQ diversity is reduced, the fact that the FAQ recognition does not affect dialogue recommendation is guaranteed, the goal of completing robot dialogue is guaranteed, a switch of FAQ response can be turned off at any time, and the stress capability is strong. The method can meet different answering scenes, the suitable answering schemes are different, the flexibility of answering strategies can be guaranteed by the splicing mode, and the on-line operation can be guaranteed after the lightweight change when new answering intents are added.

In the present specification, each embodiment of the method is described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. The relevant points can be obtained by referring to the partial description of the method embodiment.

Based on the above-mentioned interactive wake-up method for risk transaction, one or more embodiments of the present specification further provide an apparatus for interactive wake-up for risk transaction. The system may include devices (including distributed systems), software (applications), modules, components, servers, clients, etc. that use the methods described in embodiments of the present specification in conjunction with hardware where necessary to implement the apparatus. Based on the same innovative conception, embodiments of the present specification provide an apparatus as described in the following embodiments. Since the implementation scheme of the apparatus for solving the problem is similar to that of the method, the specific apparatus implementation in the embodiment of the present specification may refer to the implementation of the foregoing method, and repeated details are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.

Specifically, fig. 4 is a schematic block diagram of an embodiment of an interactive wake-up device for risk transaction provided in this specification, which may be applied in a transaction platform, as shown in fig. 4, the interactive wake-up device for risk transaction provided in this specification may include:

the risk reminding module 41 is configured to send risk reminding interactive information to a transaction user of a risk transaction to be processed, and receive risk confirmation interactive information returned by the transaction user;

the intention identification module 42 is configured to determine an interaction intention of the trading user according to the risk confirmation interaction information, and acquire interaction answering information corresponding to the interaction intention from a question and answer database;

the dialogue recommendation module 43 is configured to determine risk interaction inquiry information according to the interaction intention and the risk confirmation interaction information;

a session splicing module 44, configured to splice the interactive question answering information and the risk interactive query information to obtain risk interactive splicing information;

and the multi-round interaction module 45 is used for sending the risk interaction splicing information to the trading user so as to guide the trading user to carry out interactive awakening of multi-round risk transactions.

The interactive awakening device for risk transaction provided in the embodiment of the present specification actively interacts with a transaction user who is to process risk transaction, performs intention identification and dialogue recommendation based on information returned by the transaction user, and acquires corresponding interactive answering information based on an interactive intention of the transaction user. And splicing the determined interactive answering information and the recommended risk interactive inquiry information, and then sending the spliced interactive answering information and the recommended risk interactive inquiry information to the trading user to guide the trading user to carry out multiple rounds of interactive awakening conversations. Based on multiple rounds of conversations with transaction users, risk identification and confirmation of risk transactions are achieved, the risk identification accuracy of the risk transactions is improved, fraud means of the risk transactions can be mined, and a data base is laid for identification of subsequent risk transactions. Meanwhile, by splicing the interactive question answering information and the recommended risk interactive inquiry information, the question of the trading user is answered, the trading user can be actively guided to confirm the risk trading, the trading user can intuitively feel whether the risk trading really has the risk or not, the trading user is timely awakened, and the safety of network trading and the awakening rate of the risk trading are improved.

It should be noted that the above-mentioned apparatus may also include other embodiments according to the description of the corresponding method embodiment, such as: the construction of a question-answer database, an intention identification method and the like. The specific implementation manner may refer to the description of the above corresponding method embodiment, and is not described in detail herein.

An embodiment of the present specification further provides an interactive wake-up device for risk transaction, including: at least one processor and a memory for storing processor-executable instructions, the processor implementing the interactive wake-up method for risk transaction of the above embodiment when executing the instructions, such as:

An embodiment of the present specification further provides an interactive wake-up system for risk transaction, including: the intelligent conversation robot and the user terminal;

the intelligent dialogue robot comprises at least one processor and a memory for storing processor executable instructions, and the processor executes the instructions to realize the interactive awakening method of risk transaction in the embodiment;

It should be noted that the above description of the apparatus and system according to the method embodiments may also include other embodiments. The specific implementation manner may refer to the description of the related method embodiment, and is not described in detail herein.

The interactive wake-up device for risk transaction provided by the present specification can also be applied to various data analysis and processing systems. The system or server or terminal or device may be a single server, or may include a server cluster, a system (including a distributed system), software (applications), actual operating devices, logical gate devices, quantum computers, etc. using one or more of the methods described herein or one or more embodiments of the system or server or terminal or device, in combination with necessary end devices implementing hardware. The system for checking for discrepancies may comprise at least one processor and a memory storing computer-executable instructions that, when executed by the processor, implement the steps of the method of any one or more of the embodiments described above.

The method embodiments provided by the embodiments of the present specification can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking the example of the present invention running on a server, fig. 5 is a hardware structure block diagram of an interactive wake-up server for risk transaction in an embodiment of this specification, and the computer terminal may be the interactive wake-up server for risk transaction or the interactive wake-up device for risk transaction in the above embodiment. As shown in fig. 5, the server 10 may include one or more (only one shown) processors 100 (the processors 100 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA, etc.), a non-volatile memory 200 for storing data, and a transmission module 300 for communication functions. It will be understood by those skilled in the art that the structure shown in fig. 5 is only an illustration and is not intended to limit the structure of the electronic device. For example, the server 10 may also include more or fewer components than shown in FIG. 5, and may also include other processing hardware, such as a database or multi-level cache, a GPU, or have a different configuration than shown in FIG. 5, for example.

The non-volatile memory 200 may be used to store software programs and modules of application software, such as program instructions/modules corresponding to the interactive wake-up method for risk transaction in the embodiment of the present specification, and the processor 100 executes various functional applications and resource data updates by executing the software programs and modules stored in the non-volatile memory 200. Non-volatile memory 200 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the non-volatile memory 200 may further include memory located remotely from the processor 100, which may be connected to a computer terminal through a network. Examples of such networks include, but are not limited to, the internet, intranets, office-to-network, mobile communication networks, and combinations thereof.

The transmission module 300 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal. In one example, the transmission module 300 includes a Network adapter (NIC) that can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission module 300 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The method or apparatus provided in this specification and described in the foregoing embodiments may implement service logic through a computer program and record the service logic on a storage medium, where the storage medium may be read and executed by a computer, and implement the effects of the solutions described in the embodiments of this specification, such as:

The storage medium may include a physical device for storing information, and typically, the information is digitized and then stored using an electrical, magnetic, or optical media. The storage medium may include: devices that store information using electrical energy, such as various types of memory, e.g., RAM, ROM, etc.; devices that store information using magnetic energy, such as hard disks, floppy disks, tapes, core memories, bubble memories, and usb disks; devices that store information optically, such as CDs or DVDs. Of course, there are other ways of storing media that can be read, such as quantum memory, graphene memory, and so forth.

The above-mentioned interactive wake-up method or apparatus for risk transaction provided in this specification may be implemented in a computer by a processor executing corresponding program instructions, for example, implemented in a PC end using a c + + language of a windows operating system, implemented in a linux system, or implemented in an intelligent terminal using android and iOS system programming languages, implemented in processing logic based on a quantum computer, or the like.

It should be noted that descriptions of the apparatus, the computer storage medium, and the system described above according to the related method embodiments may also include other embodiments, and specific implementations may refer to descriptions of corresponding method embodiments, which are not described in detail herein.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the hardware + program class embodiment, since it is substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to only the partial description of the method embodiment.

The embodiments of the present description are not limited to what must be consistent with industry communications standards, standard computer resource data updating and data storage rules, or what is described in one or more embodiments of the present description. Certain industry standards, or implementations modified slightly from those described using custom modes or examples, may also achieve the same, equivalent, or similar, or other, contemplated implementations of the above-described examples. The embodiments using the modified or transformed data acquisition, storage, judgment, processing and the like can still fall within the scope of the alternative embodiments of the embodiments in this specification.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a vehicle-mounted human-computer interaction device, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

Although one or more embodiments of the present description provide method operational steps as described in the embodiments or flowcharts, more or fewer operational steps may be included based on conventional or non-inventive approaches. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When the device or the end product in practice executes, it can execute sequentially or in parallel according to the method shown in the embodiment or the figures (for example, in the environment of parallel processors or multi-thread processing, even in the environment of distributed resource data update). The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, article, or apparatus that comprises the recited elements is not excluded. The terms first, second, etc. are used to denote names, but not any particular order.

For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, when implementing one or more of the present description, the functions of each module may be implemented in one or more software and/or hardware, or a module implementing the same function may be implemented by a combination of multiple sub-modules or sub-units, etc. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable resource data updating apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable resource data updating apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable resource data update apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable resource data update apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage, graphene storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

As will be appreciated by one skilled in the art, one or more embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, one or more embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

One or more embodiments of the present description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. One or more embodiments of the present specification can also be practiced in distributed computing environments where tasks are performed by remote devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, and the relevant points can be referred to only part of the description of the method embodiments. In the description of the specification, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the specification. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

The above description is merely exemplary of one or more embodiments of the present disclosure and is not intended to limit the scope of one or more embodiments of the present disclosure. Various modifications and alterations to one or more embodiments described herein will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of the present specification should be included in the scope of the claims.

Claims

1. An interactive wake-up method of risk trading, the method comprising:

2. The method of claim 1, wherein the question-answer database is constructed by:

acquiring historical risk transaction interaction sample information;

3. The method of claim 2, after marking a query interaction log for which a query exists, the method further comprising:

the clustering the query interaction logs by a clustering algorithm comprises:

4. The method of claim 1, wherein the determining the interaction intention of the trading user according to the risk confirmation interaction information and obtaining the interaction answer information corresponding to the interaction intention from a question-answer database comprises:

5. The method of claim 1, wherein the determining the interaction intention of the trading user according to the risk confirmation interaction information and obtaining the interaction answer information corresponding to the interaction intention from a question-answer database comprises:

6. The method of claim 1, wherein determining risk interaction query information based on the interaction intent and the risk confirmation interaction information comprises:

7. The method of claim 1, wherein sending the risk interaction splicing information to the trading user to guide the trading user to perform interactive awakening of multiple rounds of risk trading comprises:

8. An interactive wake-up device for risk transactions, comprising:

9. An interactive wake-up device for risk transactions, comprising: at least one processor and a memory for storing processor-executable instructions, the processor implementing the method of any one of claims 1-7 when executing the instructions.

10. An interactive wake-up system for risk transactions, comprising: the intelligent conversation robot and the user terminal;

the intelligent dialogue robot comprising at least one processor and a memory for storing processor-executable instructions that when executed by the processor implement the method of any of claims 1-7;